Merge branch 'net-smc-two-features-for-smc-r'

Guangguan Wang says:

====================
net/smc: Two features for smc-r

v2: https://lore.kernel.org/netdev/[e-mail]/
v1: https://lore.kernel.org/oe-kbuild-all/[e-mail]/
====================

Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Paolo Abeni <[e-mail]>

net/smc/af_smc.c

···
 	ini->check_smcrv2 = true;
 	ini->smcrv2.saddr = smc->clcsock->sk->sk_rcv_saddr;
 	if (!(ini->smcr_version & SMC_V2) ||
-	    smc->clcsock->sk->sk_family != AF_INET ||
+#if IS_ENABLED(CONFIG_IPV6)
+	    (smc->clcsock->sk->sk_family == AF_INET6 &&
+	     !ipv6_addr_v4mapped(&smc->clcsock->sk->sk_v6_rcv_saddr)) ||
+#endif
 	    !smc_clc_ueid_count() ||
 	    smc_find_rdma_device(smc, ini))
 		ini->smcr_version &= ~SMC_V2;

net/smc/smc_core.c

···
 	if (lgr->smc_version == SMC_V2) {
 		lnk->smcibdev = ini->smcrv2.ib_dev_v2;
 		lnk->ibport = ini->smcrv2.ib_port_v2;
+		lnk->wr_rx_sge_cnt = lnk->smcibdev->ibdev->attrs.max_recv_sge < 2 ? 1 : 2;
+		lnk->wr_rx_buflen = smc_link_shared_v2_rxbuf(lnk) ?
+			SMC_WR_BUF_SIZE : SMC_WR_BUF_V2_SIZE;
 	} else {
 		lnk->smcibdev = ini->ib_dev;
 		lnk->ibport = ini->ib_port;
+		lnk->wr_rx_sge_cnt = 1;
+		lnk->wr_rx_buflen = SMC_WR_BUF_SIZE;
 	}
 	get_device(&lnk->smcibdev->ibdev->dev);
 	atomic_inc(&lnk->smcibdev->lnk_cnt);

net/smc/smc_core.h

···
 	} ____cacheline_aligned_in_smp;
 	struct completion	tx_ref_comp;
 
-	struct smc_wr_buf	*wr_rx_bufs;	/* WR recv payload buffers */
+	u8			*wr_rx_bufs;	/* WR recv payload buffers */
 	struct ib_recv_wr	*wr_rx_ibs;	/* WR recv meta data */
 	struct ib_sge		*wr_rx_sges;	/* WR recv scatter meta data */
 	/* above three vectors have wr_rx_cnt elements and use the same index */
+	int			wr_rx_sge_cnt; /* rx sge, V1 is 1, V2 is either 2 or 1 */
+	int			wr_rx_buflen;	/* buffer len for the first sge, len for the
+						 * second sge is lgr shared if rx sge is 2.
+						 */
 	dma_addr_t		wr_rx_dma_addr;	/* DMA address of wr_rx_bufs */
 	dma_addr_t		wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/
 	u64			wr_rx_id;	/* seq # of last recv WR */
···
 static inline bool smc_link_active(struct smc_link *lnk)
 {
 	return lnk->state == SMC_LNK_ACTIVE;
+}
+
+static inline bool smc_link_shared_v2_rxbuf(struct smc_link *lnk)
+{
+	return lnk->wr_rx_sge_cnt > 1;
 }
 
 static inline void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw)

net/smc/smc_ib.c

···
 /* create a queue pair within the protection domain for a link */
 int smc_ib_create_queue_pair(struct smc_link *lnk)
 {
-	int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1;
 	struct ib_qp_init_attr qp_attr = {
 		.event_handler = smc_ib_qp_event_handler,
 		.qp_context = lnk,
···
 			.max_send_wr = SMC_WR_BUF_CNT * 3,
 			.max_recv_wr = SMC_WR_BUF_CNT * 3,
 			.max_send_sge = SMC_IB_MAX_SEND_SGE,
-			.max_recv_sge = sges_per_buf,
+			.max_recv_sge = lnk->wr_rx_sge_cnt,
 			.max_inline_data = 0,
 		},
 		.sq_sig_type = IB_SIGNAL_REQ_WR,

net/smc/smc_llc.c

···
 }
 
 static void smc_llc_save_add_link_rkeys(struct smc_link *link,
-					struct smc_link *link_new)
+					struct smc_link *link_new,
+					u8 *llc_msg)
 {
 	struct smc_llc_msg_add_link_v2_ext *ext;
 	struct smc_link_group *lgr = link->lgr;
 	int max, i;
 
-	ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 +
+	ext = (struct smc_llc_msg_add_link_v2_ext *)(llc_msg +
 						     SMC_WR_TX_SIZE);
 	max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2);
 	down_write(&lgr->rmbs_lock);
···
 	if (rc)
 		goto out_clear_lnk;
 	if (lgr->smc_version == SMC_V2) {
-		smc_llc_save_add_link_rkeys(link, lnk_new);
+		u8 *llc_msg = smc_link_shared_v2_rxbuf(link) ?
+			(u8 *)lgr->wr_rx_buf_v2 : (u8 *)llc;
+		smc_llc_save_add_link_rkeys(link, lnk_new, llc_msg);
 	} else {
 		rc = smc_llc_cli_rkey_exchange(link, lnk_new);
 		if (rc) {
···
 	if (rc)
 		goto out_err;
 	if (lgr->smc_version == SMC_V2) {
-		smc_llc_save_add_link_rkeys(link, link_new);
+		u8 *llc_msg = smc_link_shared_v2_rxbuf(link) ?
+			(u8 *)lgr->wr_rx_buf_v2 : (u8 *)add_llc;
+		smc_llc_save_add_link_rkeys(link, link_new, llc_msg);
 	} else {
 		rc = smc_llc_srv_rkey_exchange(link, link_new);
 		if (rc)
···
 	if (lgr->smc_version == SMC_V2) {
 		struct smc_llc_msg_delete_rkey_v2 *llcv2;
 
-		memcpy(lgr->wr_rx_buf_v2, llc, sizeof(*llc));
-		llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)lgr->wr_rx_buf_v2;
+		if (smc_link_shared_v2_rxbuf(link)) {
+			memcpy(lgr->wr_rx_buf_v2, llc, sizeof(*llc));
+			llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)lgr->wr_rx_buf_v2;
+		} else {
+			llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)llc;
+		}
 		llcv2->num_inval_rkeys = 0;
 
 		max = min_t(u8, llcv2->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2);

net/smc/smc_wr.c

···
 		return; /* short message */
 	temp_wr_id = wc->wr_id;
 	index = do_div(temp_wr_id, link->wr_rx_cnt);
-	wr_rx = (struct smc_wr_rx_hdr *)&link->wr_rx_bufs[index];
+	wr_rx = (struct smc_wr_rx_hdr *)(link->wr_rx_bufs + index * link->wr_rx_buflen);
 	hash_for_each_possible(smc_wr_rx_hash, handler, list, wr_rx->type) {
 		if (handler->type == wr_rx->type)
 			handler->handler(wc, wr_rx);
···
 
 static void smc_wr_init_sge(struct smc_link *lnk)
 {
-	int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1;
 	bool send_inline = (lnk->qp_attr.cap.max_inline_data > SMC_WR_TX_SIZE);
 	u32 i;
 
···
 	 * the larger spillover buffer, allowing easy data mapping.
 	 */
 	for (i = 0; i < lnk->wr_rx_cnt; i++) {
-		int x = i * sges_per_buf;
+		int x = i * lnk->wr_rx_sge_cnt;
 
 		lnk->wr_rx_sges[x].addr =
-			lnk->wr_rx_dma_addr + i * SMC_WR_BUF_SIZE;
-		lnk->wr_rx_sges[x].length = SMC_WR_TX_SIZE;
+			lnk->wr_rx_dma_addr + i * lnk->wr_rx_buflen;
+		lnk->wr_rx_sges[x].length = smc_link_shared_v2_rxbuf(lnk) ?
+			SMC_WR_TX_SIZE : lnk->wr_rx_buflen;
 		lnk->wr_rx_sges[x].lkey = lnk->roce_pd->local_dma_lkey;
-		if (lnk->lgr->smc_version == SMC_V2) {
+		if (lnk->lgr->smc_version == SMC_V2 && smc_link_shared_v2_rxbuf(lnk)) {
 			lnk->wr_rx_sges[x + 1].addr =
 					lnk->wr_rx_v2_dma_addr + SMC_WR_TX_SIZE;
 			lnk->wr_rx_sges[x + 1].length =
···
 		}
 		lnk->wr_rx_ibs[i].next = NULL;
 		lnk->wr_rx_ibs[i].sg_list = &lnk->wr_rx_sges[x];
-		lnk->wr_rx_ibs[i].num_sge = sges_per_buf;
+		lnk->wr_rx_ibs[i].num_sge = lnk->wr_rx_sge_cnt;
 	}
 	lnk->wr_reg.wr.next = NULL;
 	lnk->wr_reg.wr.num_sge = 0;
···
 
 	if (lnk->wr_rx_dma_addr) {
 		ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr,
-				    SMC_WR_BUF_SIZE * lnk->wr_rx_cnt,
+				    lnk->wr_rx_buflen * lnk->wr_rx_cnt,
 				    DMA_FROM_DEVICE);
 		lnk->wr_rx_dma_addr = 0;
 	}
···
 
 int smc_wr_alloc_link_mem(struct smc_link *link)
 {
-	int sges_per_buf = link->lgr->smc_version == SMC_V2 ? 2 : 1;
-
 	/* allocate link related memory */
 	link->wr_tx_bufs = kcalloc(SMC_WR_BUF_CNT, SMC_WR_BUF_SIZE, GFP_KERNEL);
 	if (!link->wr_tx_bufs)
 		goto no_mem;
-	link->wr_rx_bufs = kcalloc(SMC_WR_BUF_CNT * 3, SMC_WR_BUF_SIZE,
+	link->wr_rx_bufs = kcalloc(SMC_WR_BUF_CNT * 3, link->wr_rx_buflen,
 				   GFP_KERNEL);
 	if (!link->wr_rx_bufs)
 		goto no_mem_wr_tx_bufs;
···
 	if (!link->wr_tx_sges)
 		goto no_mem_wr_tx_rdma_sges;
 	link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3,
-				   sizeof(link->wr_rx_sges[0]) * sges_per_buf,
+				   sizeof(link->wr_rx_sges[0]) * link->wr_rx_sge_cnt,
 				   GFP_KERNEL);
 	if (!link->wr_rx_sges)
 		goto no_mem_wr_tx_sges;
···
 	smc_wr_tx_set_wr_id(&lnk->wr_tx_id, 0);
 	lnk->wr_rx_id = 0;
 	lnk->wr_rx_dma_addr = ib_dma_map_single(
-		ibdev, lnk->wr_rx_bufs,	SMC_WR_BUF_SIZE * lnk->wr_rx_cnt,
+		ibdev, lnk->wr_rx_bufs,	lnk->wr_rx_buflen * lnk->wr_rx_cnt,
 		DMA_FROM_DEVICE);
 	if (ib_dma_mapping_error(ibdev, lnk->wr_rx_dma_addr)) {
 		lnk->wr_rx_dma_addr = 0;
···
 		goto out;
 	}
 	if (lnk->lgr->smc_version == SMC_V2) {
-		lnk->wr_rx_v2_dma_addr = ib_dma_map_single(ibdev,
-			lnk->lgr->wr_rx_buf_v2, SMC_WR_BUF_V2_SIZE,
-			DMA_FROM_DEVICE);
-		if (ib_dma_mapping_error(ibdev, lnk->wr_rx_v2_dma_addr)) {
-			lnk->wr_rx_v2_dma_addr = 0;
-			rc = -EIO;
-			goto dma_unmap;
+		if (smc_link_shared_v2_rxbuf(lnk)) {
+			lnk->wr_rx_v2_dma_addr =
+				ib_dma_map_single(ibdev, lnk->lgr->wr_rx_buf_v2,
+						  SMC_WR_BUF_V2_SIZE, DMA_FROM_DEVICE);
+			if (ib_dma_mapping_error(ibdev, lnk->wr_rx_v2_dma_addr)) {
+				lnk->wr_rx_v2_dma_addr = 0;
+				rc = -EIO;
+				goto dma_unmap;
+			}
 		}
 		lnk->wr_tx_v2_dma_addr = ib_dma_map_single(ibdev,
 			lnk->lgr->wr_tx_buf_v2, SMC_WR_BUF_V2_SIZE,
···
 		lnk->wr_tx_v2_dma_addr = 0;
 	}
 	ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr,
-			    SMC_WR_BUF_SIZE * lnk->wr_rx_cnt,
+			    lnk->wr_rx_buflen * lnk->wr_rx_cnt,
 			    DMA_FROM_DEVICE);
 	lnk->wr_rx_dma_addr = 0;
 out: